© 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. 153922
    Prev
    Next
    INDEX
    Explanations

    amounts and transactions

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

    specifics

    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
     "./
    0.50
     conserving
    0.50
    য়ের
    0.50
     constrained
    0.48
    しっかり
    0.45
     Constraint
    0.45
    assertEqual
    0.45
    qualiter
    0.44
     shadowy
    0.44
     preserving
    0.44
    POSITIVE LOGITS
    ，
    0.55
    Ι
    0.49
     Avila
    0.49
    ،
    0.46
     toman
    0.46
     proveedores
    0.45
    AA
    0.42
     kree
    0.42
    і
    0.42
    క
    0.41
    Activations Density 0.001%

    No Known Activations