© 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. 101675
    Prev
    Next
    INDEX
    Explanations

    transferable skills

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

    simple analogies, holographic wills, focus areas

    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
    kt
    0.43
     titel
    0.41
    铯
    0.40
    žiť
    0.40
    #}
    0.39
    県
    0.39
    eller
    0.38
    蹴
    0.38
     Segal
    0.38
    ikker
    0.37
    POSITIVE LOGITS
    փ
    0.48
     跳转
    0.48
    ቧ
    0.48
     پیسې
    0.47
     PUBLICATIONS
    0.46
     போதும்
    0.43
     Haines
    0.42
    onomics
    0.42
     فونبیټ
    0.42
     jumped
    0.42
    Activations Density 0.000%

    No Known Activations