© 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. 173178
    Prev
    Next
    INDEX
    Explanations

    pulling teeth, refundable, reimbursed, keep your

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

    black leather

    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
    तला
    0.48
     Siam
    0.47
    ை
    0.45
    ್ಣ
    0.45
     起
    0.44
     sideboard
    0.44
    ు
    0.43
    ্ড
    0.42
     คน
    0.42
     poncho
    0.42
    POSITIVE LOGITS
     خواہ
    0.49
    যথ
    0.42
    求
    0.42
     άλλ
    0.42
     esprim
    0.42
     impegn
    0.42
     demandas
    0.42
     সার্জ
    0.41
    
    0.41
    航空
    0.40
    Activations Density 0.001%

    No Known Activations