© 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-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-262K
    7. 12195
    Prev
    Next
    INDEX
    Explanations

    specific nouns and their common continuations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_22_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     fenómeno
    1.05
    arganya
    1.02
     különböz
    1.02
     îl
    1.00
    ził
    0.99
    <unused1994>
    0.97
    oprec
    0.97
    鿢
    0.97
    ającego
    0.96
    ostomy
    0.96
    POSITIVE LOGITS
     time
    0.83
     land
    0.81
     icing
    0.80
     Eve
    0.77
     right
    0.77
    0.76
     Princess
    0.75
     just
    0.74
     destined
    0.74
     G
    0.73
    Activations Density 0.000%

    No Known Activations