© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 167405
    Prev
    Next
    INDEX
    Explanations

    screens, gossip, generative

    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_40_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
     gemüt
    0.43
    癃
    0.42
    сик
    0.42
    âts
    0.42
     भागों
    0.41
     θε
    0.40
     slij
    0.40
    脓
    0.39
     dipakai
    0.39
     sân
    0.39
    POSITIVE LOGITS
     paints
    0.37
     VAR
    0.36
     predictable
    0.36
     Reporters
    0.36
     minds
    0.36
    labels
    0.35
    tní
    0.35
    deals
    0.35
     confronted
    0.35
    glue
    0.35
    Activations Density 0.000%

    No Known Activations