© 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. 10636
    Prev
    Next
    INDEX
    Explanations

    set by

    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
    ].
    0.56
    。
    0.56
    ]$.
    0.50
    ®.
    0.50
    ).
    0.49
    》。
    0.48
    %.
    0.47
    ।
    0.47
    }.
    0.46
    ។
    0.46
    POSITIVE LOGITS
     admittedly
    0.46
     insbesondere
    0.34
     recordemos
    0.34
    albeit
    0.33
    !,
    0.32
     incidentally
    0.32
     threatened
    0.31
     například
    0.31
    ,)
    0.31
     بسیار
    0.30
    Activations Density 0.268%

    No Known Activations