© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 207060
    Prev
    Next
    INDEX
    Explanations

    places with temperature control

    np_acts-logits-general · gemini-2.5-flash-lite

    shell commands and paths

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     Instructional
    0.48
    }$).
    0.46
     Recordings
    0.44
    और
    0.43
     instructional
    0.43
    oly
    0.43
    }$)
    0.42
    otrexate
    0.42
    ளையும்
    0.41
    estial
    0.41
    POSITIVE LOGITS
    ⵢ
    0.45
    することにより
    0.44
     İst
    0.44
    Proven
    0.44
     taxonom
    0.44
    ד
    0.44
     تعمیر
    0.43
    ین
    0.43
     aneu
    0.43
    Wür
    0.42
    Activations Density 0.001%

    No Known Activations