© 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. 124714
    Prev
    Next
    INDEX
    Explanations

    access control and reimbursements

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

    ejaculate, berries, artificial, voice

    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
     Confirmation
    0.50
    anderen
    0.50
     già
    0.48
    ke
    0.46
    j
    0.46
    Confirmation
    0.45
    <
    0.45
    jem
    0.45
    ck
    0.44
    ;
    0.44
    POSITIVE LOGITS
     पो
    0.46
    ,-\
    0.45
    விடும்
    0.44
    ায
    0.43
     disperse
    0.42
     වි
    0.42
     agrup
    0.42
     malignant
    0.41
     mobilize
    0.41
     $/
    0.41
    Activations Density 0.000%

    No Known Activations