© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 192847
    Prev
    Next
    INDEX
    Explanations

    instead of

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

    egg yolk remains

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    𝘦
    0.58
    ⇨
    0.48
    기
    0.48
    га
    0.47
    하면
    0.46
    ця
    0.46
    ἢ
    0.45
    미
    0.45
    しますが
    0.44
    Invitation
    0.44
    POSITIVE LOGITS
    kingen
    0.45
    }\
    0.44
     инженер
    0.44
    ruption
    0.44
    .},
    0.43
    inskii
    0.43
     despair
    0.42
    verm
    0.42
     imshow
    0.42
    maximal
    0.42
    Activations Density 0.000%

    No Known Activations