© 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-262K
    4. 40009
    Prev
    Next
    INDEX
    Explanations

    installation and setup instructions

    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
    licted
    0.42
    r
    0.40
     عمران
    0.39
     mere
    0.38
    classes
    0.38
     trophies
    0.38
    default
    0.38
     काफी
    0.38
    ঠু
    0.38
     reassuring
    0.37
    POSITIVE LOGITS
    Correo
    0.47
     الجم
    0.47
     către
    0.46
    剻
    0.46
     Corpo
    0.45
    ارہ
    0.44
    Plants
    0.43
    CCCCC
    0.42
    动脉
    0.42
     ahorita
    0.42
    Activations Density 0.001%

    No Known Activations