© 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. 12458
    Prev
    Next
    INDEX
    Explanations

    acronyms followed by nouns

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

    project specific names

    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
    analisi
    0.45
    𝔪
    0.43
    ・
    0.42
    Ґ
    0.42
    および
    0.42
    ℑ
    0.42
    áno
    0.42
    経済
    0.41
    な
    0.41
    anesulfonyl
    0.41
    POSITIVE LOGITS
     overarching
    0.40
     learnings
    0.39
     balconies
    0.39
     ছাড়াও
    0.39
     offerings
    0.38
     tardes
    0.38
     onboarding
    0.38
     liquors
    0.38
     rounds
    0.38
     frontage
    0.37
    Activations Density 0.036%

    No Known Activations