© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 11506
    Prev
    Next
    INDEX
    Explanations

    hole

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ’
    -3.06
    b
    -2.77
    u
    -2.63
    A
    -2.53
    </td>
    -2.47
    “
    -2.45
    U
    -2.36
    >
    -2.30
     戰
    -2.17
     he
    -2.09
    POSITIVE LOGITS
    </strong>
    2.97
    胧
    2.58
    inerario
    2.58
    ꜆
    2.56
     contém
    2.56
    ⑉
    2.55
    sekten
    2.52
    ଝ
    2.52
    鯪
    2.48
    翆
    2.47
    Activations Density 0.014%

    No Known Activations