© 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. 23892
    Prev
    Next
    INDEX
    Explanations

    very [something]

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

    controlling access or finding contact

    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
    iment
    0.51
    "
    0.47
    iments
    0.46
    --
    0.46
    ural
    0.44
    obao
    0.44
    舅
    0.43
    nment
    0.42
    are
    0.42
    phere
    0.42
    POSITIVE LOGITS
     demikian
    0.51
     đủ
    0.50
     ގ
    0.47
     नावा
    0.47
    s
    0.47
     आजादी
    0.47
     ป
    0.46
     निर्णय
    0.46
     आत्मविश्वास
    0.46
     drawSprites
    0.46
    Activations Density 0.000%

    No Known Activations