© 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-IT
    5. 41-GEMMASCOPE-2-RES-262K
    7. 57117
    Prev
    Next
    INDEX
    Explanations

    types of words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post_all/layer_41_width_262k_l0_big
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     overweight
    0.42
    ndarray
    0.42
     ಪ್ರಕರಣ
    0.42
     throwable
    0.41
    град
    0.40
    形状
    0.40
    }|^
    0.40
     তোর
    0.39
    featureType
    0.37
    גר
    0.37
    POSITIVE LOGITS
     reducing
    0.38
     जाना
    0.38
    -------
    0.38
     él
    0.37
     davanti
    0.37
    减
    0.37
     TECHN
    0.37
    椷
    0.36
    ---------
    0.36
    nées
    0.36
    Activations Density 0.000%

    No Known Activations