© 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. 41210
    Prev
    Next
    INDEX
    Explanations

    `:` or `"` followed by code/data

    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
     piercing
    0.46
     from
    0.45
     –
    0.45
     tattoos
    0.43
     piercings
    0.43
     streaks
    0.43
     ascension
    0.42
     tour
    0.42
     Vegan
    0.42
     travel
    0.41
    POSITIVE LOGITS
    });
    0.52
    })
    0.50
    дентификаторы
    0.47
    );
    0.43
     maxn
    0.42
     SimSun
    0.42
    ैक्ट
    0.41
     NSUTF
    0.41
     SPDX
    0.41
    obuf
    0.40
    Activations Density 0.002%

    No Known Activations