© 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-IT
    5. 31-GEMMASCOPE-2-RES-16K
    7. 5484
    Prev
    Next
    INDEX
    Explanations

    evaluative adjectives

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ،
    0.51
    ,
    0.50
     ६
    0.49
    、
    0.49
     보다
    0.49
     ۶
    0.47
     ፣
    0.46
     없고
    0.46
    +,
    0.45
    ˒
    0.43
    POSITIVE LOGITS
     (
    0.46
     The
    0.43
     the
    0.42
     M
    0.42
    SQL
    0.40
    L
    0.40
     Form
    0.40
    Wel
    0.39
     O
    0.39
    Tri
    0.39
    Activations Density 0.292%

    No Known Activations