© 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. 234071
    Prev
    Next
    INDEX
    Explanations

    regularly is, also raised, plated against

    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
    तां
    0.43
     Satisf
    0.43
    más
    0.43
    ma
    0.42
    u
    0.41
    ständ
    0.41
    Satisf
    0.41
    😕
    0.41
    જે
    0.40
    xd
    0.40
    POSITIVE LOGITS
     अभिने
    0.49
    していきます
    0.43
     multitud
    0.43
     വരുന്ന
    0.42
    復活
    0.42
     multitude
    0.42
     Фургала
    0.41
    ouvoir
    0.41
     către
    0.41
     volto
    0.40
    Activations Density 0.000%

    No Known Activations