© 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-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 10974
    Prev
    Next
    INDEX
    Explanations

    gaslighting

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_7_width_16k_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
    م
    2.35
    m
    2.19
    ो
    1.90
    l
    1.88
    h
    1.85
    <start_of_image>
    1.84
    re
    1.84
    US
    1.66
    b
    1.66
    c
    1.66
    POSITIVE LOGITS
    🩸
    2.73
    亗
    2.70
    enuhi
    2.52
     instytuc
    2.51
     undead
    2.44
    🦴
    2.44
    示す
    2.42
     hátsó
    2.41
    VCTarget
    2.40
     katana
    2.40
    Activations Density 0.022%

    No Known Activations