© 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. 1223
    Prev
    Next
    INDEX
    Explanations

    enough to

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

    enough to

    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
    TT
    0.39
    <unused60>
    0.38
     পোকামাক
    0.37
    more
    0.37
     відбувається
    0.36
     overestimated
    0.36
    </h2>
    0.35
    ão
    0.35
     és
    0.35
     emphasises
    0.35
    POSITIVE LOGITS
     enough
    0.65
    Enough
    0.63
     Enough
    0.62
     suficientes
    0.61
     genug
    0.60
    足够
    0.59
    足以
    0.59
     να
    0.59
     suficiente
    0.57
    夠
    0.57
    Activations Density 0.095%

    No Known Activations