© 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-3-270M-IT
    5. 12-GEMMASCOPE-2-RES-16K
    7. 1646
    Prev
    Next
    INDEX
    Explanations

    names and technical identifiers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-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
    .
    0.85
    </tbody>
    0.82
    就这样
    0.74
    iliate
    0.72
    。
    0.72
    还有一个
    0.71
     inhibits
    0.71
     Archa
    0.71
    }^{-
    0.71
     But
    0.70
    POSITIVE LOGITS
     McGuire
    1.46
    MaxIntensity
    1.45
     Dab
    1.45
     Букмекерская
    1.44
     DBHelper
    1.43
    Gon
    1.42
    newMark
    1.39
     Gilmore
    1.39
    Tot
    1.38
     Fitzpatrick
    1.38
    Activations Density 0.150%

    No Known Activations