© 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. 5438
    Prev
    Next
    INDEX
    Explanations

    enables or allows

    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
     تھے۔
    1.02
    ։
    0.99
     }}$.
    0.98
     تھیں۔
    0.91
    തെന്നും
    0.85
     ہیں۔
    0.85
    être
    0.84
    “.
    0.84
    }$.
    0.84
    .].
    0.82
    POSITIVE LOGITS
     helps
    3.04
     creates
    2.64
     enables
    2.63
     allows
    2.60
     reduces
    2.58
     gives
    2.56
     brings
    2.52
     eliminates
    2.46
     promotes
    2.42
     enhances
    2.42
    Activations Density 0.506%

    No Known Activations