© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 28538
    Prev
    Next
    INDEX
    Explanations

    vector and its applications

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ون
    0.88
    кого
    0.71
    ين
    0.65
     ένα
    0.64
     étend
    0.64
     می
    0.61
     이후
    0.61
    )]),
    0.59
    kiego
    0.59
     পরে
    0.59
    POSITIVE LOGITS
    Vector
    1.01
     Vector
    0.96
     vector
    0.93
    vector
    0.93
     vect
    0.90
    VECTOR
    0.87
     Vectors
    0.86
     벡터
    0.86
     vectorized
    0.84
    vect
    0.81
    Activations Density 0.018%

    No Known Activations