© 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. 37324
    Prev
    Next
    INDEX
    Explanations

    punctuation and words

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

    leaders, Create, managed

    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
     affirmations
    0.49
     but
    0.44
    jskim
    0.44
     timestamps
    0.43
    izando
    0.43
    প্তর
    0.42
    嚷
    0.42
    timestamps
    0.42
     papan
    0.42
     signatures
    0.42
    POSITIVE LOGITS
    騫
    0.49
    ก
    0.43
    客様
    0.42
    ли
    0.42
     Sorry
    0.41
    Produce
    0.41
    鉞
    0.41
    avail
    0.40
     ಮಾಡ
    0.40
    ज्
    0.40
    Activations Density 0.001%

    No Known Activations