© 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. 9095
    Prev
    Next
    INDEX
    Explanations

    languages and specific terms

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

    bail, cash, ring, spreads, evils

    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
    V
    0.40
    Akt
    0.36
    IT
    0.34
     ascertaining
    0.34
    D
    0.34
    SCR
    0.33
    PLACEMENT
    0.33
    A
    0.33
    S
    0.32
    de
    0.31
    POSITIVE LOGITS
    শিংটন
    0.40
    btnInventory
    0.37
    नरी
    0.36
     onstage
    0.35
    iktok
    0.35
     రోజు
    0.35
    饨
    0.35
     ఉంటుంది
    0.35
    uldron
    0.35
     nerdy
    0.35
    Activations Density 0.000%

    No Known Activations