© 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. 7132
    Prev
    Next
    INDEX
    Explanations

    bolding text blocks

    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
    [/
    0.44
     [/
    0.40
     IMHO
    0.40
     crappy
    0.39
     shitty
    0.38
     oddly
    0.38
     paranoia
    0.38
     ಭಾವ
    0.38
    .[/
    0.37
     horribly
    0.37
    POSITIVE LOGITS
    ~\
    0.41
    cester
    0.40
    module
    0.39
    ide
    0.38
    aeus
    0.38
    etic
    0.37
    vasive
    0.36
     Public
    0.36
    ec
    0.35
    icycle
    0.35
    Activations Density 0.000%

    No Known Activations