© 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-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 123695
    Prev
    Next
    INDEX
    Explanations

    Module, derives, ListConvolve

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_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
    q
    0.49
     },
    0.43
     пло
    0.43
    Y
    0.43
     инфра
    0.42
     '',
    0.41
     உலகில்
    0.40
     садо
    0.40
    ಿದ್ದರು
    0.40
    z
    0.40
    POSITIVE LOGITS
    ﺍ
    0.47
    Despatx
    0.46
     geändert
    0.43
    arrivée
    0.42
    حديث
    0.42
     محاضرت
    0.40
    ەم
    0.39
    גיע
    0.39
     neve
    0.39
     relatos
    0.39
    Activations Density 0.002%

    No Known Activations