© 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. 99909
    Prev
    Next
    INDEX
    Explanations

    balance and situation

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

    descriptions of states

    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
    洲
    0.52
    ác
    0.45
    áš
    0.42
    舜
    0.42
     busted
    0.42
    íš
    0.41
    andered
    0.41
    ନ
    0.41
    寶
    0.41
    ivo
    0.41
    POSITIVE LOGITS
    に対
    0.52
     plaie
    0.49
    retry
    0.48
    UH
    0.47
    Params
    0.46
    Gamma
    0.46
    SEM
    0.46
    Retry
    0.46
    EntityManager
    0.45
     مرگ
    0.45
    Activations Density 0.001%

    No Known Activations