© 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. 192194
    Prev
    Next
    INDEX
    Explanations

    galaxy granite

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

    company wanting

    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
    esehatan
    0.54
    গো
    0.47
    ເຈ
    0.46
    שר
    0.46
    ανο
    0.45
    መ
    0.45
    හෝ
    0.45
    ጤ
    0.45
     encomendas
    0.43
     इनोवेशन
    0.43
    POSITIVE LOGITS
     AZ
    0.48
     seleccionado
    0.48
     Championship
    0.45
     Chic
    0.45
     university
    0.44
     Chosen
    0.44
     keď
    0.44
     Vector
    0.43
     Wanted
    0.42
     WANTED
    0.42
    Activations Density 0.000%

    No Known Activations