© 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. 24587
    Prev
    Next
    INDEX
    Explanations

    system names, libraries, algorithms, metaphors

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

    argument passed

    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
    ח
    0.51
    हमें
    0.46
    Estoy
    0.45
    ש
    0.45
    Estamos
    0.44
    у
    0.43
    Aj
    0.43
    У
    0.43
    uli
    0.42
    वास्तव
    0.42
    POSITIVE LOGITS
     eliminate
    0.45
     safeguards
    0.45
     newly
    0.43
     Eliminate
    0.43
     nowego
    0.43
     auxiliary
    0.41
     eliminates
    0.41
     Hardware
    0.41
     supprimer
    0.41
     neuen
    0.40
    Activations Density 0.000%

    No Known Activations