© 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. 17125
    Prev
    Next
    INDEX
    Explanations

    beauty is, line and, as removal

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

    asking about specific items

    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
    These
    0.52
    這些
    0.49
    これらの
    0.48
    Actress
    0.45
    여러
    0.45
    お
    0.44
    这些
    0.44
    ๑
    0.44
    วาม
    0.43
    CTED
    0.43
    POSITIVE LOGITS
     थंड
    0.46
     उलट
    0.45
     χω
    0.44
     liger
    0.43
     مقار
    0.42
     قریب
    0.42
     broj
    0.41
     κα
    0.41
     (!
    0.41
    zicht
    0.41
    Activations Density 0.000%

    No Known Activations