© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-16K
    7. 9688
    Prev
    Next
    INDEX
    Explanations

    composed 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_16k_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
    }$.
    2.48
    }$
    2.39
    ä
    2.36
    }$,
    2.08
    }$-
    1.91
    ИН
    1.86
    }$$
    1.83
    are
    1.82
    ০
    1.80
    마
    1.80
    POSITIVE LOGITS
    ن
    2.02
    gments
    1.96
    ه
    1.84
    yaw
    1.81
    gement
    1.80
    de
    1.77
    gadas
    1.74
    gning
    1.74
    ్య
    1.73
    naden
    1.72
    Activations Density 0.048%

    No Known Activations