© 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. 40-GEMMASCOPE-2-RES-262K
    4. 8056
    Prev
    Next
    INDEX
    Explanations

    state immutability and mutations

    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_40_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
    াসা
    0.41
    Female
    0.41
    บค
    0.39
    闗
    0.38
    一线
    0.38
    female
    0.38
    Saharan
    0.38
    閫
    0.37
    閂
    0.37
    \{(
    0.36
    POSITIVE LOGITS
    state
    0.73
     state
    0.70
     immutable
    0.63
    newState
    0.57
     Immutable
    0.52
    currentState
    0.50
     newState
    0.48
    Mutable
    0.47
    immutable
    0.47
     devlet
    0.47
    Activations Density 0.005%

    No Known Activations