© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 2849
    Prev
    Next
    INDEX
    Explanations

    right?

    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
    or
    1.50
     whom
    1.44
     God
    1.34
     vanqu
    1.31
    asses
    1.27
    ass
    1.27
     I
    1.26
     Carroll
    1.22
     Lord
    1.22
     who
    1.22
    POSITIVE LOGITS
    lerde
    1.75
     μόνο
    1.67
    করিতে
    1.65
    일상
    1.65
    lidir
    1.63
    হইতে
    1.61
    lere
    1.60
     musí
    1.58
    勎
    1.56
    də
    1.56
    Activations Density 0.113%

    No Known Activations