© 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. 136852
    Prev
    Next
    INDEX
    Explanations

    insurance conversion day cake

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

    concise expressions of possibility

    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
     .”
    0.49
    ା
    0.46
     яке
    0.46
     .)
    0.45
    Scient
    0.43
    ٫
    0.43
     ."
    0.42
     ].
    0.40
     시간이
    0.39
    .=
    0.39
    POSITIVE LOGITS
    politik
    0.53
     עבור
    0.49
    דר
    0.46
     für
    0.46
     deaktiv
    0.45
     mochila
    0.44
     führ
    0.43
     plunder
    0.43
    כה
    0.42
    לק
    0.42
    Activations Density 0.007%

    No Known Activations