© 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. 160915
    Prev
    Next
    INDEX
    Explanations

    centre, last, her, tastings

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

    avoid paying, merge sort, spread outwards, classic tourist

    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
    )=>
    0.48
    ższe
    0.44
    த்தில்
    0.43
     よろしく
    0.42
     અમારી
    0.42
    "})
    0.42
     சிறிய
    0.42
    "=
    0.42
    Buf
    0.41
    "=>
    0.41
    POSITIVE LOGITS
    aat
    0.45
     wanneer
    0.45
    rase
    0.44
    otta
    0.44
    エース
    0.42
     quando
    0.41
     tecl
    0.41
     dissociate
    0.41
     aonde
    0.41
    ።
    0.41
    Activations Density 0.000%

    No Known Activations