Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-4B-IT
    3. 29-GEMMASCOPE-2-RES-262K
    4. 1036
    Prev
    Next
    INDEX
    Explanations

    bracketed numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_29_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
     /
    0.81
     `/
    0.78
     '+'
    0.77
     /=
    0.77
     alphabet
    0.76
     regex
    0.75
     "+"
    0.74
    /_
    0.72
    isNaN
    0.72
    /")
    0.72
    POSITIVE LOGITS
    ⇓
    1.24
    ].
    1.11
    ].”
    1.07
    –
    1.06
    <unused1958>
    1.01
    “.
    1.00
    ••
    1.00
    ]).
    0.98
    ],
    0.96
     letteratura
    0.95
    Activations Density 0.039%

    No Known Activations