© 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. 137356
    Prev
    Next
    INDEX
    Explanations

    water requirementsWonder womanmen achievethen allowconfidence

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

    similar instrumentation, within appropriate

    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
     (§
    0.48
     島
    0.48
     progressing
    0.46
     gacch
    0.44
     ఉ
    0.43
     בק
    0.43
    ತ್ವ
    0.43
     (†
    0.42
    startTimestamp
    0.42
     実
    0.42
    POSITIVE LOGITS
    尽量
    0.46
     benutzer
    0.44
    يمه
    0.44
    ضل
    0.43
     conjectures
    0.43
    同样的
    0.42
    上述
    0.41
    যাত্র
    0.41
     Administ
    0.40
    做
    0.40
    Activations Density 0.001%

    No Known Activations