© 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-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-262K
    7. 1303
    Prev
    Next
    INDEX
    Explanations

    critique of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_12_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
    },
    1.82
    }$
    1.72
    ן
    1.64
    }
    1.62
    い
    1.60
    }>
    1.55
    ב
    1.54
    ள்
    1.51
    }$$
    1.51
    係る
    1.51
    POSITIVE LOGITS
    यर
    1.52
    on
    1.43
    afe
    1.41
    as
    1.38
     WF
    1.34
     batsmen
    1.30
    et
    1.29
    сист
    1.29
    aar
    1.23
    oost
    1.22
    Activations Density 0.016%

    No Known Activations