© 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. 175168
    Prev
    Next
    INDEX
    Explanations

    know how, internal or, economical comb

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

    between common questions

    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
     வால்பேப்ப
    0.47
    Ⴀ
    0.46
     вой
    0.46
    ส์
    0.46
    力が
    0.45
    ून्य
    0.44
     기준으로
    0.44
     snowflakes
    0.44
     throwIf
    0.44
    یت
    0.43
    POSITIVE LOGITS
    an
    0.60
    5
    0.49
    permit
    0.48
    ol
    0.47
    malign
    0.47
    onde
    0.46
    a
    0.45
    casino
    0.45
    tube
    0.45
    ondan
    0.45
    Activations Density 0.001%

    No Known Activations