© 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. 78735
    Prev
    Next
    INDEX
    Explanations

    through the, working as, her lead, from the

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

    GPU, CPU, RAM, VRAM

    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
     refractory
    0.50
     tubing
    0.47
    s
    0.45
     compatibility
    0.45
     ref
    0.41
    an
    0.40
    mation
    0.40
     tween
    0.39
     kidnapping
    0.38
     inquiet
    0.38
    POSITIVE LOGITS
     Ανα
    0.58
     Debit
    0.52
     Haha
    0.51
    СТЕ
    0.49
    妘
    0.49
    ᕼ
    0.49
    क्र
    0.49
    веро
    0.49
     JESUS
    0.48
    २०
    0.47
    Activations Density 0.001%

    No Known Activations