© 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. 27050
    Prev
    Next
    INDEX
    Explanations

    includes three, interesting advantages

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

    counting number of 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
    Mayo
    0.47
    aderos
    0.45
    َّ
    0.42
    另一
    0.41
    LOCATION
    0.41
    ో
    0.41
    滢
    0.40
    颦
    0.39
    ню
    0.39
    RULES
    0.38
    POSITIVE LOGITS
     ff
    0.49
     ორი
    0.48
    āna
    0.44
     Wonderful
    0.44
     ies
    0.43
     Fb
    0.43
     dva
    0.42
     FF
    0.42
     nd
    0.40
     dst
    0.40
    Activations Density 0.000%

    No Known Activations