© 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. 121073
    Prev
    Next
    INDEX
    Explanations

    images gallery descriptions

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

    injection, acquisition, encryption

    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
     ቡ
    0.50
     gau
    0.44
    atthakath
    0.42
     honti
    0.42
    ]++;
    0.42
     gels
    0.42
     ramifications
    0.42
     المتع
    0.41
    ক্ত
    0.41
    vae
    0.41
    POSITIVE LOGITS
    ریت
    0.47
    充电
    0.46
     NIST
    0.45
    တယ်။
    0.43
    嫋
    0.43
    charging
    0.43
    আনু
    0.43
     Town
    0.42
    town
    0.42
    月から
    0.42
    Activations Density 0.001%

    No Known Activations