© 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. 145933
    Prev
    Next
    INDEX
    Explanations

    ruin any chance or ethics without

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

    worldly salvation

    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
     сн
    0.51
    인다
    0.50
     км
    0.48
    ዢ
    0.46
     центр
    0.45
    <0xE4>
    0.45
    蝸
    0.45
    ์
    0.45
     особен
    0.44
    ใ
    0.44
    POSITIVE LOGITS
     spectators
    0.45
     t
    0.44
    یم
    0.43
     presumably
    0.42
     Haf
    0.40
     during
    0.40
     accompanying
    0.40
     fertilized
    0.40
     auraient
    0.40
     unseren
    0.40
    Activations Density 0.001%

    No Known Activations