© 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. 188040
    Prev
    Next
    INDEX
    Explanations

    compiling reports

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

    marketing copy generation

    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
     […]
    0.51
     أن
    0.50
     أخ
    0.50
     ï
    0.50
    an
    0.48
    bart
    0.47
     компьютера
    0.47
     VA
    0.47
     jaja
    0.47
    esen
    0.46
    POSITIVE LOGITS
    ೊಳ್ಳ
    0.49
    NotDefined
    0.47
    </thead>
    0.46
    いだ
    0.46
     distaste
    0.46
     enforceable
    0.45
    হাই
    0.45
    後は
    0.45
     sequels
    0.44
     postulated
    0.44
    Activations Density 0.000%

    No Known Activations