© 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. 200398
    Prev
    Next
    INDEX
    Explanations

    phrases starting certain topics

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

    biblical tone, threats, claims, disrupting traditional

    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
    事前に
    0.56
    ラ
    0.55
    주
    0.54
    주고
    0.53
    ку
    0.51
    라
    0.51
    비
    0.50
    하이
    0.48
     जेटली
    0.46
    리
    0.46
    POSITIVE LOGITS
    டாக
    0.45
     gleichen
    0.44
    microphone
    0.44
     آهنگ
    0.43
    ≥
    0.43
     ≥
    0.43
    amit
    0.43
    identifier
    0.42
    ᵢ
    0.42
    aram
    0.42
    Activations Density 0.000%

    No Known Activations