© 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. 70372
    Prev
    Next
    INDEX
    Explanations

    following leader or obeyed

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

    quantifying status or conditions

    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
    ارض
    0.49
     AMD
    0.48
     concealed
    0.46
     LX
    0.45
     kesulitan
    0.45
    AMD
    0.45
    VIEW
    0.44
    [/
    0.44
    _
    0.44
     archivo
    0.44
    POSITIVE LOGITS
    avorites
    0.45
    깐
    0.45
    ｇ
    0.44
    succ
    0.43
     мероприя
    0.42
     リュック
    0.42
    ர்க்
    0.41
    𝗋
    0.41
    tempCard
    0.41
    Labs
    0.41
    Activations Density 0.001%

    No Known Activations