© 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. 189695
    Prev
    Next
    INDEX
    Explanations

    company name suffix

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

    email, growth, personalities, theater, quick

    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
     grading
    0.47
    <%@
    0.47
     Orr
    0.46
     nausea
    0.45
    .
    0.43
     ACR
    0.42
    ↵
    0.42
    <strong>
    0.42
     octave
    0.42
    /
    0.41
    POSITIVE LOGITS
    enthalt
    0.53
     municípios
    0.52
     Timurtaş
    0.50
    wijl
    0.50
    tze
    0.50
    etição
    0.50
     баскетбол
    0.50
     பயன்படுத்தி
    0.49
     말미암아
    0.49
    partite
    0.49
    Activations Density 0.001%

    No Known Activations