© 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. 194177
    Prev
    Next
    INDEX
    Explanations

    non-english characters and common words

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

    specific details or requirements

    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
    0.60
     तन
    0.55
    )
    0.54
    vcn
    0.54
    ]
    0.52
    ء
    0.51
    UM
    0.51
     τρόπο
    0.51
    :=
    0.50
     pristup
    0.49
    POSITIVE LOGITS
     Denis
    0.44
    โค
    0.43
     identifier
    0.42
    טו
    0.42
     specified
    0.41
     చే
    0.40
    িপ
    0.40
     additionally
    0.40
     taip
    0.40
    ಹಿತ
    0.39
    Activations Density 0.000%

    No Known Activations