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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 13935
    Prev
    Next
    INDEX
    Explanations

    concept + preposition/completion

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

    evaluative adjectives or descriptors

    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
    Not in Any Lists

    No Comments

    Negative Logits
     ,
    0.34
     and
    0.34
     aka
    0.32
     (
    0.32
     և
    0.30
     three
    0.29
     và
    0.29
     dwie
    0.29
     dubbed
    0.28
     as
    0.28
    POSITIVE LOGITS
    ０
    0.32
    ঘ্রই
    0.31
    ুর
    0.30
    してる
    0.30
    原来的
    0.30
    >')
    0.29
    nextProps
    0.29
    以外
    0.29
    rarse
    0.29
    কাতে
    0.28
    Activations Density 0.033%

    No Known Activations