© 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. 16-GEMMASCOPE-2-RES-262K
    7. 41483
    Prev
    Next
    INDEX
    Explanations

    corsica, scorching sun

    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
    ]
    0.98
    ;
    0.97
    س
    0.96
    -
    0.95
    $
    0.93
    }
    0.91
    "
    0.89
    Countries
    0.88
    ],
    0.87
    .}
    0.86
    POSITIVE LOGITS
     be
    1.17
    er
    0.95
     can
    0.95
    t
    0.92
    ри
    0.90
    l
    0.86
    social
    0.84
     on
    0.84
    system
    0.81
     not
    0.81
    Activations Density 0.001%

    No Known Activations