© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 232622
    Prev
    Next
    INDEX
    Explanations

    signs, writing, hosting, rings, information

    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
    气氛
    0.47
    囩
    0.47
    in
    0.46
     음악
    0.44
    姆斯
    0.43
     عط
    0.42
     క్
    0.42
    рсә
    0.42
    abelle
    0.41
    谄
    0.41
    POSITIVE LOGITS
     VRS
    0.49
    ದ್ದರಿಂದ
    0.49
     hospitalization
    0.48
     decision
    0.46
     নয়াদ
    0.46
     MERCHANTABILITY
    0.45
    ];
    0.45
     décision
    0.45
     बहु
    0.45
     PSU
    0.45
    Activations Density 0.000%

    No Known Activations