© 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. 29164
    Prev
    Next
    INDEX
    Explanations

    location names

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

    scikit-learn estimators

    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
     prognosis
    0.52
    ämp
    0.46
     lounges
    0.46
     effluents
    0.46
    𝙈
    0.46
    adati
    0.45
     précision
    0.45
    ))
    0.44
    آور
    0.44
     เร
    0.44
    POSITIVE LOGITS
    都
    0.49
     Trabal
    0.46
    يں
    0.45
    人不
    0.45
     Tư
    0.43
     Native
    0.42
     Castel
    0.42
    Camel
    0.42
    Tech
    0.42
    Subscribe
    0.41
    Activations Density 0.000%

    No Known Activations