© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-65K
    4. 13556
    Prev
    Next
    INDEX
    Explanations

    links

    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_65k_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
     niềm
    0.48
     nhưng
    0.46
    ualitas
    0.46
    /@
    0.45
     Với
    0.45
     sidebar
    0.44
     persuas
    0.44
     infantile
    0.44
     terus
    0.43
     euphoria
    0.43
    POSITIVE LOGITS
    the
    0.56
    મ
    0.53
    www
    0.51
    প
    0.46
    la
    0.43
    اي
    0.43
    von
    0.42
    le
    0.40
    1
    0.40
     Tuna
    0.39
    Activations Density 0.040%

    No Known Activations