© 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. 28614
    Prev
    Next
    INDEX
    Explanations

    understand how things work

    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
    zantine
    0.45
    vény
    0.44
    fühl
    0.39
    étel
    0.39
    ॉम
    0.38
    纽约
    0.36
     पुरंदरे
    0.36
    ނ
    0.35
    逦
    0.35
     ادی
    0.35
    POSITIVE LOGITS
     skies
    0.42
     Boolean
    0.41
     decimal
    0.37
     north
    0.37
     integer
    0.36
     self
    0.36
    _{
    0.35
     je
    0.35
     apex
    0.35
     variables
    0.35
    Activations Density 0.003%

    No Known Activations