© 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. 59005
    Prev
    Next
    INDEX
    Explanations

    birthday cards, save money, find people

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

    Stay quiet and hidden

    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
    ující
    0.52
    が見
    0.52
     عنها
    0.51
    voja
    0.51
    _"+
    0.51
     رم
    0.50
    㤟
    0.49
     करुन
    0.49
    㐹
    0.49
    ImgBoard
    0.48
    POSITIVE LOGITS
    t
    0.45
     leaky
    0.44
     assaults
    0.43
     the
    0.42
    세
    0.42
    insieme
    0.42
    Upsilon
    0.42
     endorph
    0.41
     chords
    0.41
     Hickey
    0.41
    Activations Density 0.000%

    No Known Activations