© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 81580
    Prev
    Next
    INDEX
    Explanations

    listing and descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     således
    -1.23
     CERTAIN
    -1.13
    亵
    -1.12
    advert
    -1.08
    %)$
    -1.08
    ARANCE
    -1.07
    titled
    -1.05
    ⏱
    -1.05
    fordable
    -1.04
    🔘
    -1.04
    POSITIVE LOGITS
     name
    2.36
     whether
    2.17
     date
    2.13
     description
    1.96
     where
    1.94
     number
    1.94
     any
    1.91
     how
    1.84
     brief
    1.84
     what
    1.79
    Activations Density 0.100%

    No Known Activations