© 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. 104053
    Prev
    Next
    INDEX
    Explanations

    other seasons

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

    various languages and concepts

    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
     TPM
    0.51
     понрави
    0.47
    த்தில்
    0.44
    illator
    0.43
    ^{\#}\
    0.42
    ȩ
    0.42
     செயற்க
    0.42
    }-
    0.42
    heatmap
    0.42
    )^{*}\
    0.41
    POSITIVE LOGITS
     guérir
    0.44
     flexibilidad
    0.42
     tief
    0.41
     sensibil
    0.41
     doma
    0.41
     personnaliser
    0.41
     profond
    0.41
    erro
    0.39
     rapproche
    0.39
    テイ
    0.39
    Activations Density 0.001%

    No Known Activations