Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B-IT
    3. 40-GEMMASCOPE-2-RES-262K
    4. 30017
    Prev
    Next
    INDEX
    Explanations

    LSTMs

    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
    த்த
    0.45
    FindFileData
    0.41
    ﺪ
    0.39
    謖
    0.39
    TARGET
    0.39
    ในการ
    0.39
    ramine
    0.39
    तिया
    0.38
    SUBJECT
    0.38
    粦
    0.38
    POSITIVE LOGITS
     SST
    0.50
     PST
    0.50
    HST
    0.49
     HST
    0.47
     ST
    0.45
     RST
    0.45
     MST
    0.43
     STS
    0.42
     regarde
    0.41
     IST
    0.40
    Activations Density 0.003%

    No Known Activations