© 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. 53-GEMMASCOPE-2-RES-262K
    7. 66448
    Prev
    Next
    INDEX
    Explanations

    licenses and distributions

    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_53_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
     substantive
    0.47
    ଞ
    0.44
     substance
    0.42
    ثت
    0.42
     específicos
    0.42
     subst
    0.41
     Subst
    0.41
     específicamente
    0.41
     specifico
    0.40
    瑚
    0.40
    POSITIVE LOGITS
    itorial
    0.49
     genial
    0.45
     Loud
    0.45
     rep
    0.44
     Rep
    0.43
     parcial
    0.41
     hosts
    0.40
     Slam
    0.40
     Why
    0.39
    Port
    0.39
    Activations Density 0.000%

    No Known Activations