© 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-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-16K
    7. 1661
    Prev
    Next
    INDEX
    Explanations

    keyword followed by colon

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_22_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
    </em>
    0.75
    െങ്ക
    0.73
    ”、“
    0.72
    </i>
    0.72
    ֣
    0.64
     있다면
    0.64
    eslint
    0.64
    不了
    0.64
    ”“
    0.63
    etc
    0.62
    POSITIVE LOGITS
    ):
    3.05
    :");
    2.94
    ():
    2.94
    :\
    2.75
    ":
    2.70
    ]:
    2.68
    ':
    2.67
    "):
    2.66
    :</
    2.65
    :**
    2.65
    Activations Density 2.829%

    No Known Activations