© 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. 19249
    Prev
    Next
    INDEX
    Explanations

    assessing monetary value

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

    discussion of policy and value

    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
     ك
    0.49
    يه
    0.47
     isch
    0.46
    uerpo
    0.45
    ちゃんの
    0.44
    nonce
    0.44
     الك
    0.44
     הק
    0.44
     pate
    0.44
     گ
    0.42
    POSITIVE LOGITS
    이제
    0.44
    अधिकांश
    0.42
    ebilirsiniz
    0.41
    忽视
    0.40
    ampunk
    0.40
    <unused2150>
    0.40
     얘기
    0.40
    🟦
    0.40
    ચારી
    0.39
     hypersonic
    0.39
    Activations Density 0.000%

    No Known Activations