© 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. 177949
    Prev
    Next
    INDEX
    Explanations

    always/never advice

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

    always do or consult

    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
     mutlaka
    0.50
    ">•
    0.44
     inevitably
    0.43
    ֜
    0.43
    ysuckle
    0.42
    ಫ್
    0.41
     quiero
    0.41
     ಫಲ
    0.41
     বিক্ষোভ
    0.40
     unbedingt
    0.40
    POSITIVE LOGITS
    smaller
    0.46
     عندما
    0.44
    有时候
    0.44
    때
    0.42
    sometimes
    0.42
    such
    0.42
    iata
    0.41
    machines
    0.41
     पाण्याच्या
    0.41
    sides
    0.41
    Activations Density 0.024%

    No Known Activations