© 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
    2. Gemma-3-27B-IT
    3. 16-GEMMASCOPE-2-RES-262K
    4. 4417
    Prev
    Next
    INDEX
    Explanations

    Forms and Input UI elements

    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_16_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
    ing
    0.75
     PTSD
    0.72
    }');
    0.62
    of
    0.61
    er
    0.60
     ofthe
    0.59
     nakon
    0.58
     Kyrgyzstan
    0.58
    alal
    0.57
    ,
    0.57
    POSITIVE LOGITS
    ка
    0.70
    נ
    0.64
    на
    0.63
    ת
    0.61
    ד
    0.58
    ্যান
    0.57
    ם
    0.57
    ковий
    0.56
    益
    0.55
    ться
    0.54
    Activations Density 0.006%

    No Known Activations