© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 55296
    Prev
    Next
    INDEX
    Explanations

    contextual cues

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

    segmentation, phases, structure

    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
     출
    0.54
    вори
    0.50
     விரை
    0.49
    ъ
    0.47
     особи
    0.47
    出
    0.46
    },\
    0.46
    成績
    0.45
    ските
    0.44
    受賞
    0.43
    POSITIVE LOGITS
     تحریک
    0.51
     cardio
    0.48
    ထိ
    0.47
     mechanism
    0.46
     doped
    0.44
     tokenizer
    0.44
     layering
    0.44
     déplacer
    0.44
     डायरेक्शन
    0.43
     piezoelectric
    0.43
    Activations Density 0.000%

    No Known Activations