© 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. 56831
    Prev
    Next
    INDEX
    Explanations

    contrasting or hypothetical statements

    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
     STILL
    0.50
     ভাল
    0.42
    IEN
    0.42
    Still
    0.40
     стреми
    0.39
     ከፍተኛ
    0.39
    仍然
    0.38
    具
    0.37
     этой
    0.37
    IGENCE
    0.36
    POSITIVE LOGITS
     realities
    0.46
     realistic
    0.41
     detachment
    0.41
     realism
    0.40
     soprattutto
    0.39
     savons
    0.39
     separate
    0.38
     realist
    0.38
    ෝ
    0.38
     sabe
    0.38
    Activations Density 0.056%

    No Known Activations