© 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. 40754
    Prev
    Next
    INDEX
    Explanations

    CSS margin and layout

    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
    <
    0.41
     Legend
    0.40
     Bulb
    0.38
     Random
    0.36
     Faun
    0.36
     Gift
    0.36
     marginBottom
    0.35
     Bl
    0.35
     jog
    0.35
    offsetHeight
    0.35
    POSITIVE LOGITS
     завжди
    0.45
    മതി
    0.43
    🛣
    0.43
     운
    0.42
    }^{+},
    0.41
     опу
    0.41
    IKV
    0.41
     logistical
    0.40
    🏖
    0.40
     확보
    0.40
    Activations Density 0.027%

    No Known Activations