© 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. 117482
    Prev
    Next
    INDEX
    Explanations

    money matters

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

    causes and consequences

    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
    хия
    0.45
     quantified
    0.44
     limiting
    0.43
    캥
    0.43
     dominance
    0.43
    2
    0.41
     vraie
    0.40
     multiplicative
    0.40
    看的
    0.40
    ัง
    0.39
    POSITIVE LOGITS
     إلى
    0.50
     Theater
    0.47
     企业
    0.46
     एमटीएस
    0.45
     ब
    0.45
     सहाय
    0.45
     باشید
    0.44
     უფრო
    0.44
    Inscription
    0.43
     Helping
    0.43
    Activations Density 0.000%

    No Known Activations