© 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
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 13255
    Prev
    Next
    INDEX
    Explanations

    questions starting with what is

    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
     എന്ത
    0.49
    *}$
    0.47
     effectuées
    0.46
    嗦
    0.45
    gx
    0.45
    <unused88>
    0.44
    న్నారు
    0.44
    Methylsulfanyl
    0.43
     무엇
    0.43
    궜
    0.41
    POSITIVE LOGITS
     the
    0.89
    the
    0.71
     teh
    0.71
     a
    0.66
     la
    0.65
     an
    0.64
     its
    0.57
     on
    0.56
     un
    0.56
    การ
    0.55
    Activations Density 0.072%

    No Known Activations