© 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. 127748
    Prev
    Next
    INDEX
    Explanations

    Park Trip

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

    versatility or specific item

    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
    ಗೂ
    0.47
     правил
    0.47
    い
    0.47
    檄
    0.47
     క్ష
    0.45
    ലം
    0.45
    בק
    0.44
    Ⲉ
    0.44
    ક્ષ
    0.43
     horrors
    0.43
    POSITIVE LOGITS
     हथ
    0.49
    inderung
    0.47
     ecologically
    0.45
    วน
    0.45
     અથ
    0.44
    ceramic
    0.43
    equ
    0.43
    iremos
    0.42
    ónicos
    0.42
    ANGMAR
    0.42
    Activations Density 0.000%

    No Known Activations