© 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. 174420
    Prev
    Next
    INDEX
    Explanations

    young man, youth

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

    discussing illegality and harm

    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
    :
    0.58
     Websites
    0.53
     Example
    0.49
    resources
    0.48
     originalmente
    0.47
    .:
    0.46
    ністю
    0.46
    ;
    0.46
     She
    0.46
     Illuminated
    0.46
    POSITIVE LOGITS
     सवार
    0.46
    RIK
    0.45
     молодых
    0.44
     कमजोर
    0.44
     യുവാ
    0.43
     युव
    0.43
     फर्क
    0.43
    年輕
    0.43
    渡し
    0.42
    看的
    0.41
    Activations Density 0.000%

    No Known Activations