© 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. 151054
    Prev
    Next
    INDEX
    Explanations

    ranking them, objected to, noted on

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

    human babies and mammals

    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
    ائرة
    0.47
    瀕
    0.45
    影
    0.44
    ἑ
    0.44
    ábban
    0.44
    Routes
    0.44
    一行
    0.43
    妵
    0.43
    的這個
    0.43
    ání
    0.42
    POSITIVE LOGITS
     reprinted
    0.53
     as
    0.52
     drills
    0.49
     holster
    0.49
     by
    0.48
     discuss
    0.48
     wearer
    0.48
    TIP
    0.47
     be
    0.47
     puedan
    0.46
    Activations Density 0.000%

    No Known Activations