© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 78712
    Prev
    Next
    INDEX
    Explanations

    ownership, midway, handgun, close

    np_acts-logits-general · gemini-2.5-flash-lite

    tailoring content for an audience

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    骗
    0.46
     roommates
    0.44
     voldoende
    0.41
     Narendra
    0.41
     Bedarf
    0.41
     Dana
    0.40
     Tanks
    0.40
     Heiz
    0.39
    جلس
    0.39
     Št
    0.39
    POSITIVE LOGITS
    ᓂ
    0.49
    犢
    0.49
    STATUS
    0.49
     retrieve
    0.48
     እየ
    0.46
     మరియు
    0.46
    ECM
    0.46
    SAME
    0.46
    ມັນ
    0.46
    동산
    0.46
    Activations Density 0.000%

    No Known Activations