© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 32938
    Prev
    Next
    INDEX
    Explanations

    academic journal references

    np_acts-logits-general · gemini-2.5-flash-lite

    the names (often abbreviated) of academic journals or publications, as they appear in reference citations.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     also
    -1.41
     one
    -1.27
     get
    -1.22
     enables
    -1.20
     people
    -1.19
     oddly
    -1.16
     difficult
    -1.16
     weirdly
    -1.15
     there
    -1.14
     because
    -1.14
    POSITIVE LOGITS
    cels
    1.21
    >>>>>>>>
    1.20
    を
    1.16
     praticamente
    1.16
     getNome
    1.14
    __((
    1.13
    しかし
    1.13
    がありますが
    1.13
     NORMAL
    1.12
    ztes
    1.12
    Activations Density 0.005%

    No Known Activations