© 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. 145754
    Prev
    Next
    INDEX
    Explanations

    advert link, property research

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

    qualifications and exceptions

    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
     sixth
    0.53
     seventh
    0.48
     Sixth
    0.45
    راجعه
    0.44
    createSprite
    0.44
    ্কার
    0.42
    Sixth
    0.41
    f
    0.41
     fifth
    0.40
     devout
    0.40
    POSITIVE LOGITS
    Nhap
    0.46
    ），
    0.42
    调度
    0.42
    ()),
    0.42
     بیم
    0.41
    ग
    0.41
    ）,
    0.40
    あ
    0.40
    ),
    0.40
     extrait
    0.39
    Activations Density 0.002%

    No Known Activations